Leukemia Classification using Deep Belief Network

Wannipa Sae-Lim, Wiphada Wettayaprasit, and Pattara Aiyarak


deep belief network, restricted Boltzmann machine, neural networks, microarray data


This paper proposes a novel approach for leukemia classification based on the use of Deep Belief Network (DBN). DBN is a feedforward neural network with a deep architecture that consists of a stack of restricted Boltzmann machine (RBM). The study used the benchmark DNA microarray of leukemia data from Kent Ridge Bio-medical Data Set Repository. The classification performance was compared between the proposed method and the traditional neural networks. In conclusion, the DBN outperforms the state-of-the-art learning models such as support vector machine (SVM), k-nearest neighbor (KNN) and Naive Bayes (NB).

Important Links:

Go Back